jbd2: add support for avoiding data writes during transaction commits

Currently when filesystem needs to make sure data is on permanent
storage before committing a transaction it adds inode to transaction's
inode list. During transaction commit, jbd2 writes back all dirty
buffers that have allocated underlying blocks and waits for the IO to
finish. However when doing writeback for delayed allocated data, we
allocate blocks and immediately submit the data. Thus asking jbd2 to
write dirty pages just unnecessarily adds more work to jbd2 possibly
writing back other redirtied blocks.

Add support to jbd2 to allow filesystem to ask jbd2 to only wait for
outstanding data writes before committing a transaction and thus avoid
unnecessary writes.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

3 files changed, 24 insertions, 5 deletions

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2ad98d6e19f4..70078096117d 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -219,6 +219,8 @@ static int journal_submit_data_buffers(journal_t *journal,
 
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+		if (!(jinode->i_flags & JI_WRITE_DATA))
+			continue;
 		mapping = jinode->i_vfs_inode->i_mapping;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
@@ -256,6 +258,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+		if (!(jinode->i_flags & JI_WAIT_DATA))
+			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 435f0b26ac20..b31852f76f46 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -94,7 +94,8 @@ EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
 EXPORT_SYMBOL(jbd2_journal_invalidatepage);
 EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
-EXPORT_SYMBOL(jbd2_journal_file_inode);
+EXPORT_SYMBOL(jbd2_journal_inode_add_write);
+EXPORT_SYMBOL(jbd2_journal_inode_add_wait);
 EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 67c103867bf8..be56c8ca34c2 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2462,7 +2462,8 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
 /*
  * File inode in the inode list of the handle's transaction
  */
-int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
+static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
+				   unsigned long flags)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal;
@@ -2487,12 +2488,14 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
 	 * and if jinode->i_next_transaction == transaction, commit code
 	 * will only file the inode where we want it.
 	 */
-	if (jinode->i_transaction == transaction ||
-	    jinode->i_next_transaction == transaction)
+	if ((jinode->i_transaction == transaction ||
+	    jinode->i_next_transaction == transaction) &&
+	    (jinode->i_flags & flags) == flags)
 		return 0;
 
 	spin_lock(&journal->j_list_lock);
-
+	jinode->i_flags |= flags;
+	/* Is inode already attached where we need it? */
 	if (jinode->i_transaction == transaction ||
 	    jinode->i_next_transaction == transaction)
 		goto done;
@@ -2523,6 +2526,17 @@ done:
 	return 0;
 }
 
+int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode)
+{
+	return jbd2_journal_file_inode(handle, jinode,
+				       JI_WRITE_DATA | JI_WAIT_DATA);
+}
+
+int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode)
+{
+	return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA);
+}
+
 /*
  * File truncate and transaction commit interact with each other in a
  * non-trivial way.  If a transaction writing data block A is